Replies: 4 comments 1 reply
-
UPDATE: I have tried to load it using the Symbol API, but still no luck: import warnings
with warnings.catch_warnings():
warnings.simplefilter('ignore')
deserialized_net = gluon.nn.SymbolBlock.imports('model_algo-1-symbol.json', ['data'], 'model_algo-1-0000.params', ctx=mx.cpu()) Error:
|
Beta Was this translation helpful? Give feedback.
-
You can try to visualize the graph and see how many inputs are there: https://mxnet.apache.org/versions/1.1.0/faq/visualize_graph.html |
Beta Was this translation helpful? Give feedback.
-
Hi Dennis, thanks for reaching out. I will look into this and get back to you soon |
Beta Was this translation helpful? Give feedback.
-
Hi Dennis, would it be possible for you to provide the model files and input so that I can try to reproduce the issue? Also which doc did you follow? |
Beta Was this translation helpful? Give feedback.
-
Hi!
I am very new to mxnet, using it for the first time and having some issues loading an AWS Sagemaker trained model for local inference, I was earlier piggy backing off this thread.
The main issue that I am having is that there is no error! My code runs fine, but the results are not as expected...
I am trying to load a model and predict on new data using the following code:
The code runs but the output is a single value rather than a distribution over topics as I would expect:
Would really appreciate some help/advice here!
Beta Was this translation helpful? Give feedback.
All reactions